_ registry / mcp streamable-http · checked 17m ago

copybook

https://copybook.page

Registry code: e347a86785e99b60

api record

Search in English. match passes lexical checks, not verified suitability; related can still fit. Judge title, summary, tools and paste. Ask only if no card fits or the request is vague; say when nothing fits. search_tips browses; get_tip reads full assets or known URLs directly. For one repo need, find_snippets returns only the parts to paste; pass a chosen slug. Judge each part against the repo and skip existing rules. Copy exactly as written, name the paste destination and show file text before writing. Preserve source URLs and returned marks. check_installed needs a Copybook sign-in and…

endpoint
https://copybook.page/mcp/account
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is copybook live?
Yes — it answered the hub's last check (checked 17m ago). It answered 100% of checks over the last 30 days.
Is copybook free to use?
Yes — the hub reached it with no key and no payment.
What tools does copybook have?
5 tools: get_tip, find_snippets, check_installed, list_facets, search_tips.
Is copybook safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
375ms

last good check

priced tools
0

of 5 tools

_ answered our checks, 90 days 1 checks · signed record
  • unknown → live
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 5 tools
2 open 3 never probed 2 of 5 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • list_facets open 17m ago

    List filter ids, plain names, technical terms and current tip counts for search_tips. Counts exclude broken and superseded tips.

    mcp-tool

    {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "properties": {}
    }
    arguments 5 lines
  • search_tips open 17m ago

    Searches Copybook's catalog of prompts, rules, skills and setups for coding agents by an English task, with optional kind, topic and tool filters (list_facets lists their values). sort: saves orders by most saved; the default is relevance with a query and newest without. Returns compact cards with the exact paste text, dated saves and the latest check. state: match passes lexical checks, not verified suitability; related can still fit; none means no card. get_tip returns a whole tip; find_snippets(need, slug) returns the parts of one tip a repo needs.

    mcp-tool

    {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "properties": {
        "kind": {
          "enum": [
            "prompt",
            "rules",
            "skill",
            "plugin",
            "mcp",
            "subagent",
            "command",
            "config"
          ],
          "type": "string",
          "description": "Kind id: prompt, rules, skill, plugin, mcp, subagent, command or config; list_facets gives names and counts."
        },
        "sort": {
          "enum": [
            "relevance",
            "newest",
            "saves"
          ],
          "type": "string",
          "description": "Order: relevance with a query, newest without (defaults); saves means most saved on X."
        },
        "tool": {
          "enum": [
            "claude-code",
            "codex",
            "cursor",
            "pi",
            "grok",
            "gemini",
            "any"
          ],
          "type": "string",
          "description": "Tool id: claude-code, codex, cursor, pi, grok, gemini or any; list_facets gives current counts."
        },
        "limit": {
          "type": "integer",
          "default": 3,
          "maximum": 20,
          "minimum": 1,
          "description": "Maximum number of candidates: 1 to 20, default 3. Candidates can be uncertain; check state."
        },
        "query": {
          "type": "string",
          "maxLength": 200,
          "description": "Words or a request in English, up to 200 characters; leave out to list by sort."
        },
        "topic": {
          "enum": [
            "ship",
            "design",
            "long-runs",
            "review",
            "repo",
            "writing",
            "models"
          ],
          "type": "string",
          "description": "Topic id: repo (Codebase), review (Review), design (Design), long-runs (Long runs), models (Models and cost), ship (Launch), writing (Writing)."
        }
      }
    }
    arguments 67 lines
  • get_tip unknown never probed

    Returns one complete tip: its exact Copy assets, three steps, notes, dated saves, latest check, playbooks and related slugs. Takes a slug, a Copybook or voxyz.ai tip URL (English or Chinese) or an X/twitter.com post URL, so a known reference needs no search. An unknown reference returns uncertain suggestions. Install IDs and source lines come from find_snippets; get_tip has none.

    mcp-tool

    {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "required": [
        "slug"
      ],
      "properties": {
        "slug": {
          "type": "string",
          "maxLength": 2048,
          "minLength": 1,
          "description": "A slug, a copybook.page or voxyz.ai tip URL in either language, or the tip's X/twitter.com post URL. Known hosts also work without https://."
        }
      }
    }
    arguments 15 lines
  • find_snippets unknown never probed

    Returns, word for word, the parts of a tip that meet one concise English repo need. The need is a short phrase: no code, file contents, paths or secrets. With slug, it reads that tip alone. state fit: whole blocks or named checklist sections; menu: the tip fits but no part was selected (get_tip has the whole text); none: no part selected (search_tips lists candidates). Each part carries its source line, the tip URL with a mark that check_installed reads later, and its durability, check age and models and conflicts_with. Missing metadata means unknown.

    mcp-tool

    {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "required": [
        "need"
      ],
      "properties": {
        "need": {
          "type": "string",
          "maxLength": 200,
          "minLength": 1,
          "description": "One concise English task, up to 200 characters, e.g. limit unrelated code edits. Omit repo/framework details unless essential. Never code, file contents, paths or secrets."
        },
        "slug": {
          "type": "string",
          "pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$",
          "maxLength": 120,
          "minLength": 1,
          "description": "Optional: a tip already chosen, from a search card, to answer for that tip alone."
        }
      }
    }
    arguments 22 lines
  • check_installed unknown 17m ago

    Checks Copybook text already in a repo by the IDs in its From Copybook source lines: <slug>#<8 hex> (the slug of the source URL with each block or unit ID), up to 100, IDs only (no paths or file contents). Each ID is current (the tip still has that text; local edits are not checked) or changed (the tip no longer has it). Also reports each tip as live, superseded (with its replacement) or retired (its latest check broke), with checks and durability. Without IDs, get_tip returns the current text to compare. Needs a Copybook sign-in; without one, the result's message says how to sign in from this client.

    mcp-tool

    {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "required": [
        "ids"
      ],
      "properties": {
        "ids": {
          "type": "array",
          "items": {
            "type": "string",
            "pattern": "^([a-z0-9]+(?:-[a-z0-9]+)*)#([0-9a-f]{8})(?:-[1-9]\\d{0,2})?$",
            "maxLength": 140
          },
          "maxItems": 100,
          "minItems": 1,
          "description": "The IDs from the source lines above Copybook text in the repo, up to 100, each <slug>#<8 hex>: the slug from the line's URL, then each block or units ID. Never file contents or paths."
        }
      },
      "additionalProperties": false
    }
    arguments 21 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id e347a86785e99b60.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/e347a86785e99b60/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/e347a86785e99b60/badge.svg)](https://brick.blue/agent/e347a86785e99b60?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
90%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.